Collaborative Research: Directed Enzyme Evolution Accelerated by Machine Learning for Enhancing the Biodegradation of Emerging Contaminants Collaborative Research: Directed Enzyme Evolution Accelerated by Machine Learning for Enhancing the Biodegradation of Emerging Contaminants A plethora of organic contaminants with anthropogenic origin have attracted extensive public attention given their frequent detection in aquatic environments. However, the presence of natural biocatalysts capable of efficiently decomposing these contaminants is inadequate since these are human-synthetic compounds. There is therefore an urgent need of exploring efficient ways of degrading these compounds. Motivated by the fact that nature has provided enzymes to catalyze specific chemical reactions with these contaminant compounds as reactants however with low efficiency, we plan to mimic nature evolution in the laboratory to optimize the catalytic power of these enzymes. One major challenge is how we can understand the molecular determinants on the efficiency of the enzyme and the underlying principles to accelerate our artificial evolution. Through integrating experiments and simulations such that theoretical models will learn key molecular factors for predicting enzyme performance from existing experimental data and then provide new enzyme variants for wet-lab test, we plan to apply an optimal feedback loop to efficiently explore the sequence space with optimal degrading performance. Dr. Wenwei Zheng will conduct the research in the third proposed step at ASU in close collaboration with PI Dr. Mengyan Lis group. Machine learning together with all-atom simulations will be applied to predicting the enzyme performance and investigating the interactions between the enzyme and contaminating compounds. The expected outcome of the computational work is to provide designing principles in optimizing the performance of these enzymes, which can dramatically accelerate the wet-lab exploration of enzyme sequence space of Dr. Lis group
|Effective start/end date||9/1/22 → 8/31/25|
- National Science Foundation (NSF): $168,791.00
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.